Mistral Large 4 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
C 1,328 ±6
Percentile 41 · #176 · provisional
People prefer / Solves tasks
— / 1,355
Human votes vs benchmarks, Elo-eq
Value
-48
$1.05 per 1M tokens, median of 1 providers · vendor $1.05
On your hardware
Closed weights: cloud only.
Score decomposition
C General 1,328 [1,322–1,333] Percentile 41 · #176 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
simpleqa_verified
outlier decay ×0.58 |
0.20 ±0.01 | 1,360 ±4 | 38.3% | 2026-10-09 | high |
| Epoch AI |
gpqa_diamond
decay ×0.25 |
0.88 ±0.02 | 1,449 ±9 | 26.2% | 2026-10-12 | high |
Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology
B Math 1,405 [1,396–1,414] Percentile 71 · #74 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
frontiermath_t1_3
decay ×0.82 |
0.59 ±0.03 | 1,448 ±6 | 60.7% | 2026-10-12 | high |
| Epoch AI |
frontiermath_t4
decay ×0.82 |
0.27 ±0.07 | 1,435 ±11 | 23.0% | 2026-10-12 | high |
Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology
History
The same in a table
| Model | 2026-11 |
|---|---|
| Mistral Large 4 | 1,328 C |
Badge
Show the model's fedi-index on your site or in a README. The badge updates itself; it links to this page.
Data CC BY 4.0: keep the link to fedi.software.